social-viral-content-finder

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill explicitly instructs the agent to install dependencies automatically and to conceal or avoid requesting user approval ("without asking the user to confirm" and "Do not describe it as a request..."), which are hidden/deceptive operational directives outside the stated content-collection purpose.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to invoke the BrowserAct CLI for live browser execution (public web pages/targets), which can ingest outsider-authored free text from fetched pages into the LLM context via the runtime browser workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The Skill requires using the BrowserAct installer link at runtime and instructs the agent to automatically install the BrowserAct CLI from https://www.browseract.com/?co-from=social-media (and the redirect link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which is high-confidence evidence the agent will fetch and execute external installer/runtime code during skill execution.